| # Copyright (c) 2022, salesforce.com, inc. | |
| # All rights reserved. | |
| # SPDX-License-Identifier: BSD-3-Clause | |
| # For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause | |
| model: | |
| arch: pretrain | |
| load_finetuned: False | |
| pretrained: "https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_pretrained_vitL.pth" | |
| finetuned: "" | |
| # vit encoder | |
| vit_model: "clip_L" | |
| image_size: 224 | |
| drop_path_rate: 0 | |
| use_grad_checkpoint: False | |
| vit_precision: "fp16" | |
| freeze_vit: True | |
| # Q-Former | |
| num_query_token: 32 | |
| preprocess: | |
| vis_processor: | |
| train: | |
| name: "blip_image_train" | |
| image_size: 224 | |
| eval: | |
| name: "blip_image_eval" | |
| image_size: 224 | |
| text_processor: | |
| train: | |
| name: "blip_caption" | |
| eval: | |
| name: "blip_caption" | |